Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis

Warning

This publication doesn't include Faculty of Economics and Administration. It includes Faculty of Medicine. Official publication website can be found on muni.cz.

Authors	PIJACKOVA Kristyna NEJEDLÝ Petr KREMEN Vaclav PLESINGER Filip MIVALT Filip LEPKOVA Kamila PAIL Martin JURAK Pavel WORRELL Gregory BRÁZDIL Milan KLIMES Petr
Year of publication	2023
Type	Article in Periodical
Magazine / Source	JOURNAL OF NEURAL ENGINEERING
MU Faculty or unit	Faculty of Medicine
Citation
Web	https://iopscience.iop.org/article/10.1088/1741-2552/acdc54
Doi	http://dx.doi.org/10.1088/1741-2552/acdc54
Keywords	intracranial EEG; genetic algorithms; optimization; neural network; deep learning
Attached files	Genetic_algorithm_designed_for_optimization_of_neural_network_architectures_for_intracranial_EEG_recordings_analysis.pdf
Description	Objective. The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data. Approach. We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification. Main results. Our method improved the macro F1 score of the state-of-the-art model in two independent datasets, from St. Anne's University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively. Significance. By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar's test, p MUCH LESS-THAN 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models' performance.
Related projects:	Národní ústav pro neurologický výzkum